Execute Markdown plans as dependency-ready task DAGs: every task in its own Git worktree, independently verified before it integrates, with durable recovery evidence and human-reviewed PR delivery. Requires Git. Works in Claude Code and Codex.
Plugin plan-runner from marketplace esper in MisterVitoPro/esper. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
prInternal plan-runner step (invoked by the run skill at pipeline end, not run directly): push the run-owned integration branch and open or update a proper pull request -- conventional title, rich structured body (task outcomes, whole-branch diff, bug counts, stats), and a smart draft/ready default ba
runRun a free-form Markdown implementation plan as a dependency-ready task DAG. Each cycle: analyze the plan into a task graph, run every ready task in its own disposable Git worktree (at most 6 at once), gate it with deterministic checks and an independent verifier, integrate verified commits onto a r
plan-aggregatorplan-runner pipeline agent that reads all per-task bug JSONs from a pipeline run, deduplicates and ranks bugs (P0-P3), produces a human-readable bugs.md summary, and generates a free-form Markdown fix-plan.md that is valid input for a re-run of the Plan Runner run skill.
plan-analyzerplan-runner pipeline agent that reads a free-form Markdown implementation plan and returns a structured task graph: stable task IDs, explicit dependency edges, file ownership, TDD roles, and verification scope for dependency-ready DAG scheduling.
plan-devplan-runner pipeline agent that implements a single task from a task graph. Generic template -- the orchestrator parameterizes each invocation with the specific task title, excerpt, owned files, acceptance criteria, and Context7 flag.
plan-integratorplan-runner central-integration protocol and conflict adjudicator. Defines how a task commit's ownership, stale base, deterministic-check evidence, and independent verdict are validated before it is serially applied to the run-owned integration branch.
plan-test-authorplan-runner pipeline agent that writes ONLY the failing tests for one testable task from a task graph. It never writes implementation -- a downstream impl agent makes the tests pass. Returns the test files and test IDs it added.
plan-verifierplan-runner pipeline agent that independently verifies ONE task attempt against its acceptance criteria. Reads the task's committed work in its own worktree, the ownership evidence, and the gate logs; flags every gap as a structured bug entry.
node -e "const fs=require('fs');try{const p='.gitignore',e='**/plan-runner/';if(fs.existsSync(p)){const c=fs.readFileSync(p,'utf8');if(!c.split(/\r?\n/).some(l=>l.trim()===e)){fs.appendFileSync(p,(c.l
Claude Code and Codex quality pipeline: deploy parallel security, correctness, performance, architecture, data-flow, and concurrency reviewers; rank and corroborate evidence-backed findings; generate a fix spec and test plan; then implement selected fixes through a test-first loop.
2 skills · 16 agents
Generate a navigable, version-controlled multi-page Markdown wiki from a codebase, engineered for on-demand retrieval as Claude's context while staying human-readable. Two-pass outline-then-fill generation across a parallel agent swarm of planner, diagram author, page writers, and index synthesizer; consumes a code-atlas index as ground truth when present, else self-scans. Pure static Markdown (no embeddings), Mermaid diagrams derived from the dependency graph, per-page source provenance, and git-blob hash-diff staleness detection that regenerates only stale pages. A SessionStart hook loads the wiki index at session start
2 skills · 6 agents · hooks
Claude Code and Codex architecture index generator: scan a codebase once, load the curated map at session start, refresh it incrementally, and query its semantic dependency graph deterministically for dependencies, impact analysis, blast radius, and risk filters; the map skill upserts a marker-delimited usage block into CLAUDE.md/AGENTS.md so later sessions consult the atlas
3 skills · 4 agents · hooks
Vulnerability-aware dependency upgrade orchestrator across 7 ecosystems (npm, Python, Go, Rust, Java, Kotlin, C#); detects outdated packages, queries OSV.dev for CVEs, recommends the safest-yet-most-recent version per package, then executes wave-by-wave with build/typecheck/test verification and clean git rollback on failure
2 skills · 4 agents · hooks
Claude Code and Codex idea-to-build pipeline: turn a raw idea into an audited design spec through a token-conscious interview with scope-sized batched questions, a category-coverage elicitation floor, an existing-system baseline, and a resumable three-status ledger. A binding ledger audit and biggest-miss critic gate the EARS-based spec. After approval, the Ideas plan skill emits a plan-runner-ready flat task list with full criteria plus a script-generated bundle: a planned source skeleton, a versioned skeleton manifest, and a typed dependency graph with a self-contained per-task Graph context. A completion gate offers a /clear-then-paste plan-runner handoff (fresh context for the execution engine), inline or subagent execution, GitHub tickets, or stop. The Ideas tickets skill projects ready tasks to a parent issue plus linked sub-issues using the gh CLI. Specs, plans, and ADRs land under the project's existing docs root, auto-detected. Not for typos, renames, or one-line fixes.
3 skills · 2 agents
Consolidate scattered specs into a canonical master-spec tree with a navigable index, and append stubs for undocumented public surface found in code
2 skills · 2 agents
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.